CClaude Cert Prep
D127% of exam

Frequently Confused Concepts — Agentic Architecture & Orchestration (CCA-F Domain 1)

Five look-alike pairs from Domain 1, compared side by side — so you pick the architecturally-correct orchestration mechanism for a scenario instead of pattern-matching on vocabulary.

12 min read Reviewed July 25, 2026
On this page

Domain 1 questions rarely ask "what is a subagent?" They hand you a scenario — a migration across 40 files, a research task with three independent lookups, a rule that a secret must never reach a tool — and ask which mechanism fits. The distractors are almost always the adjacent concept: the one that shares vocabulary but plays a different architectural role. If you only memorized definitions, both answers look right.

This guide attacks that directly. Each section takes a pair that test-writers love to blur and pulls them apart along the dimensions that actually decide a question: who makes the decision, when it happens, what it does to the context window, and what it is for. The goal is a mental model you can run in your head, not a glossary you recite.

A quick orientation before the pairs. An agent is a loop: the model proposes an action, the harness executes it, the result feeds back, and the loop repeats until the model stops. Two facts fall out of that. First, some things are decided by the model (which tool to call, whether to spawn help) and some are decided by the harness around it (whether a hook fires, whether tool calls in one turn run concurrently) — confusing those two actors is the single most common Domain 1 mistake. Second, every subagent gets its own fresh context window and hands back only a distilled result, which is the whole reason the pattern exists. Keep the actor and the context window in mind and the five pairs below mostly answer themselves.

Coordinator vs Subagent

These are two roles in the same delegation, not two competing tools — which is exactly why they get swapped. The coordinator (also called the orchestrator or lead agent) is the agent that holds the plan, decides what to farm out, and stitches results together. A subagent is a worker it spawns to run one focused subtask in an isolated context and return a distilled answer. One thinks about the whole job; the other executes a slice of it and reports back.

DimensionCoordinatorSubagent
PurposePlan the overall task, delegate slices, integrate results into a final answerExecute one bounded subtask and return a condensed result
ScopeThe whole objective, end to endA single slice defined by the prompt it was handed
Who decidesThe coordinator model chooses what to spawn and whenThe subagent model decides only how to accomplish its assigned slice
Context windowLong-lived; holds the plan and the final synthesized answers (not each worker's raw scratch work)Fresh and isolated — sees only the prompt passed in, not the parent's history
LifetimeSpans the entire sessionLives only for its one subtask, then terminates
Best forMulti-part goals needing planning, routing, and synthesisIsolating a noisy or specialized job (deep search, focused audit) so its tokens never bloat the parent
When NOT to useA single simple task with no parts to coordinate — delegating adds pure overheadA step that needs the parent's full running context, or that must interact turn-by-turn with the user

Coordinator vs Task tool

This pair confuses a design role with the mechanism that implements it. The coordinator is the architectural pattern — an agent that orchestrates. The Task tool (surfaced as the Task/Agent tool) is the concrete capability the coordinator invokes to actually spawn a subagent. Saying "use a coordinator" describes intent; "call the Task tool" describes the button that makes it happen. A coordinator that never calls Task has simply chosen not to delegate yet.

DimensionCoordinator (role)Task tool (mechanism)
PurposeBe the orchestrating agent that plans and delegatesProvide the actual call that launches a subagent with a prompt
CategoryA design pattern / responsibilityA tool in the model's toolset
Who decidesN/A — it is the deciding agentThe coordinator model decides whether and how to call it
When it appearsWhenever a task needs orchestrationOnly at the moment delegation is chosen — one invocation per subagent
Context behaviourRetains the plan and integrates returned resultsEach invocation opens a new isolated context for the child and returns its result to the parent
Best forDescribing what structure a solution needsDescribing the specific step that creates a worker
When NOT to useDon't call it a tool — it is a roleDon't treat it as a strategy — spawning is a step, not a plan

Sequential execution vs Parallel Task calls

Both are ways to run multiple pieces of work; the difference is a dependency graph. Sequential execution means each step consumes the previous step's output, so they must be serialized — step 2 literally cannot start without step 1's result. Parallel Task calls means the subtasks are independent, so the coordinator can emit several Task invocations in a single turn and let them run concurrently, then gather the results. The deciding question is never speed for its own sake — it's whether the inputs of one step depend on the outputs of another.

DimensionSequential executionParallel Task calls
Core conditionSteps are dependent — later needs earlier's outputSubtasks are independent — none needs another's result
OrderingStrict order; each waits for the priorNo required order; they fan out at once
How it's expressedOne action per turn, feeding the nextMultiple Task calls issued together in the same turn
Who decidesThe model, based on data flow between stepsThe model, once it judges the subtasks share no state
LatencySum of all steps (slow but necessary)Roughly the slowest single subtask (concurrent)
Best forPipelines: fetch → transform → validate → actFan-out: three independent lookups, per-file audits, breadth-first research
When NOT to useDon't serialize truly independent work — you waste timeDon't parallelize dependent steps — a worker would run on missing or stale input

Prompt chaining vs Dynamic decomposition

Both break a big job into smaller steps; the difference is who authors the steps and when. Prompt chaining is a fixed, pre-planned pipeline — you, the designer, wire step 1 → step 2 → step 3 ahead of time, and every run follows that same path. Dynamic decomposition is the agentic loop generating and revising subtasks at runtime — the agent looks at what it just learned and decides what to do next, so the shape of the work isn't known until it runs. Static structure you designed vs. structure the agent discovers.

DimensionPrompt chainingDynamic decomposition
Who plans the stepsThe human designer, in advanceThe agent, at runtime, as it learns
When steps are fixedBefore any run — the pipeline is hard-wiredNever fully — the plan adapts to findings
Path per runSame every timeVaries with the inputs and intermediate results
PredictabilityHigh — auditable, testable, repeatableLower — flexible but harder to fully predict
AdaptivityNone; unexpected inputs fall off the railsHigh; can branch, add, or drop subtasks mid-task
Best forWell-understood, stable workflows (extract → translate → format)Open-ended tasks where the needed steps depend on what's found (debugging, research, exploration)
When NOT to useWhen the required steps can't be known up frontWhen you need strict, repeatable, auditable behavior every run

Hooks vs Tool use

This is the pair that most often decides a hard Domain 1 question, because it hinges on which actor is in control. Tool use is a capability the model chooses to invoke inside the loop — it may call a tool, or not, based on its judgment. A hook (e.g. PreToolUse, PostToolUse) is deterministic enforcement the harness runs around tool calls, entirely outside the model's discretion — it fires every time its event occurs, and a PreToolUse hook can block a tool call before it happens. Tool use is a choice; a hook is a guarantee.

DimensionHooksTool use
Who decides / runs itThe harness — configured, deterministic, not up to the modelThe model — it elects to call the tool
DiscretionNone; fires on its event every timeFull; the model may skip or choose a different tool
When it runsAutomatically at a lifecycle point (before/after a tool call)Whenever the model emits a tool call in its turn
Guarantee levelDeterministic — a PreToolUse hook can hard-block the actionProbabilistic — depends on the model deciding correctly
PurposeEnforce policy: validate, log, redact, deny, or gate an actionExtend capability: fetch data, run code, act on the world
Best forRules that must hold every time regardless of the model ("never let a secret reach this tool")Getting information or performing actions the model needs
When NOT to useDon't use a hook to add optional capability the model should reason aboutDon't rely on tool use / prompting to enforce a hard safety rule the model could skip

Key takeaways

  • 01Coordinator and subagent are two roles in one delegation: the coordinator plans, routes, and integrates; the subagent executes one isolated slice and returns a distilled result.
  • 02Every subagent gets a fresh, isolated context window and hands back only a summary — that isolation is the entire reason to use one.
  • 03A coordinator is a design role; the Task/Agent tool is the mechanism it calls to spawn a subagent. Role vs mechanism, noun vs verb.
  • 04Sequential vs parallel is decided by dependencies, not by a wish for speed: output-feeds-input must serialize; truly independent subtasks fan out in one turn.
  • 05Prompt chaining is a fixed pipeline the designer wires in advance; dynamic decomposition is the agent generating and revising steps at runtime as it learns.
  • 06Tool use is model-chosen capability; a hook is harness-run, deterministic enforcement (PreToolUse/PostToolUse) that fires every time and can block an action.
  • 07The recurring discriminator across Domain 1: identify the actor — is the model deciding, or is the harness enforcing?
  • 08"Always / never / enforce / regardless of the model" signals a hook; "decide / when appropriate / if needed" signals tool use.

Common mistakes

Calling the coordinator a tool, or the Task tool a strategy.

Keep the layers straight: the coordinator is the orchestrating role, the Task/Agent tool is the concrete call that spawns a subagent. One is a responsibility, the other is an action.

Parallelizing subtasks because the stem says 'for efficiency,' even when one step needs another's output.

Check the dependency graph first. If output A feeds input B, they must run sequentially no matter how much faster parallel sounds. Only fan out genuinely independent work.

Labeling any multi-step agent 'dynamic decomposition' (or any decomposition 'prompt chaining') because both split work into steps.

Decide by authorship and timing: steps fixed by the designer before the run = prompt chaining; steps the agent generates and revises at runtime = dynamic decomposition.

Trusting a tool call or a system-prompt instruction to guarantee a 'never'/'always' safety rule.

Anything the model chooses can be skipped. For a hard guarantee, use a deterministic PreToolUse/PostToolUse hook the harness runs outside the model's discretion.

Assuming a subagent can see the parent's conversation, files already read, or prior decisions.

Subagents start with a fresh, isolated context. Put every path, error message, and decision the worker needs directly into the prompt you pass when spawning it.

Frequently asked

Is a coordinator just a subagent that happens to delegate?

No — they're distinct roles. The coordinator owns the overall plan and integrates results across the whole task; a subagent handles one isolated slice and returns a distilled answer. A coordinator can itself be a subagent of a higher-level agent, but within a given delegation the planner/integrator is the coordinator and the focused worker is the subagent.

If the Task tool is how you spawn a subagent, why distinguish it from the coordinator at all?

Because exam questions test the difference between a role and a mechanism. 'Use a coordinator' describes the architecture you want; 'call the Task tool' is the specific action that realizes it. A question asking for the mechanism wants the Task tool; one asking for the pattern wants the coordinator.

How do I tell in the moment whether steps should be sequential or parallel?

Trace the data. If any step reads a previous step's output, that link must be sequential. If you can give every subtask all its inputs up front and none depends on another, issue them as parallel Task calls in one turn. Speed is a consequence, not the deciding factor.

Isn't dynamic decomposition just prompt chaining with more steps?

No. Step count is irrelevant. Prompt chaining is a pipeline whose steps are fixed before the run and identical every time; dynamic decomposition is the agent inventing and revising steps at runtime based on what it discovers. A ten-step fixed pipeline is still chaining; a two-step adaptive plan is still decomposition.

Why can't I just prompt the model to 'always' do something instead of writing a hook?

Because a prompt or a tool the model chooses can be skipped, misjudged, or reasoned around — it's probabilistic. A hook is run deterministically by the harness at a lifecycle point (e.g. PreToolUse) and can block the action before it happens, so it delivers the every-time guarantee that safety and audit requirements demand.

Independent, unofficial study material. Not affiliated with, endorsed by, or authorized by Anthropic. Every example is original and written to teach the public exam objectives — no real exam questions are reproduced. Technical details reflect Claude, the Anthropic API, Claude Code, and MCP as of July 25, 2026; always confirm specifics against current official documentation.

Test yourself

Turn what you just read into answers you can check.

Take the mock exam

Keep studying

All guides

These guides are free and never paywalled. Keep Claude Cert Prep free ♥